git-message
Skill0 starsChanged 41 days agoMITView on GitHub
Use when the agent needs to write a Git commit message from staged or unstaged changes. Mention "commit message", "write a commit", or "conventional commit" as triggers.
- Commits and pushes
1 other project uses a version of this.
Adopted by
Most recently taken up by
- marslo/skillstheir own version, first seen Sep 2, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- marslo/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository45 other files it gives its agents.
- admission-policy-reviewSkill
- alert-rule-reviewSkill
- architecture-reviewSkill
- argocd-applicationsetSkill
- argocd-debugSkill
- argocdSkill
- cert-manager-debugSkill
- cicd-reviewSkill
- cilium-debugSkill
- ciliumSkill
- cluster-backupSkill
- dast-reviewSkill
- dockerfile-reviewSkill
- english-technical-messageSkill
- gitops-reviewSkill
- go-bugfixSkill
- go-code-reviewSkill
- go-testing-reviewSkill
- grafana-dashboardsSkill
- helm-reviewSkill
- homelab-change-planSkill
- incident-analysisSkill
- ingressSkill
- interview-system-designSkill
- istio-debugSkill
- istioSkill
- kubernetes-autoscalingSkill
- kubernetes-debugSkill
- kubernetes-securitySkill
- kubernetes-yaml-reviewSkill
- migration-planSkill
- observability-reviewSkill
- observability-stackSkill
- production-readinessSkill
- pr-reviewSkill
- root-cause-analysisSkill
- runbook-writerSkill
- runtime-security-reviewSkill
- secrets-managementSkill
- storage-debugSkill
- supply-chain-securitySkill
- terraform-reviewSkill
- upgrade-readinessSkill
- vaultSkill
- vulnerability-triageSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Use read-only git diff --staged or git diff to inspect the actual change.
- Distinctive: line 22
Do not invent a change the diff does not contain.
- Distinctive: line 26
Follow the Workflow, Safety rules, and Quality checklist below.
- Distinctive: line 36
Use when the user asks for a commit message, wants help writing one from a diff, or asks to follow Conventional Commits for a change that …
- Very specific: line 52
Check for breaking changes.
- Distinctive: line 60
Do not run git commit, git push, or stage files automatically unless the user explicitly asks you to.
- Distinctive: line 62
Do not invent details not visible in the diff or supplied by the user — if intent is unclear, say so instead of guessing.
- Distinctive: line 64
Never include secrets, tokens, or credentials that may appear in a diff.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Git Message
TL;DR checklist
- Read staged changes, or unstaged diff if nothing is staged.
- Choose the conventional type and useful scope.
- Write an imperative subject and a body explaining motivation and context.
Key read-only checks
- Use read-only
git diff --stagedorgit diffto inspect the actual change.
Common pitfalls
- Do not invent a change the diff does not contain.
Agent procedure
Follow the Workflow, Safety rules, and Quality checklist below.
Quick references
- Workflow below.
Last verified: unverified
When to use
Use when the user asks for a commit message, wants help writing one from a diff, or asks to follow Conventional Commits for a change that is staged, unstaged, or described in words.
Goal
Produce a high-quality, Conventional-Commits-style commit message that explains why the change was made, not just what changed.
Workflow
- Inspect the diff (
git diff --staged, falling back togit diffif nothing is staged). - Identify the change type:
feat,fix,refactor,docs,test,chore,perf,ci,build,style. - Identify the scope (package, module, or service touched), if it adds clarity.
- Draft a subject line:
<type>(<scope>): <imperative summary>, ≤72 characters. - Draft a body: explain motivation and context, not a line-by-line restatement of the diff.
- Check for breaking changes; if present, add a
BREAKING CHANGE:footer describing the impact and migration path. - Note any risk (e.g. touches shared config, no tests added, affects a hot path) as a short "Risk notes" line.
- Suggest the exact
git commitcommand the user can run, but do not run it yourself.
Safety rules
- Do not run
git commit,git push, or stage files automatically unless the user explicitly asks you to. - Do not invent details not visible in the diff or supplied by the user — if intent is unclear, say so instead of guessing.
- Never include secrets, tokens, or credentials that may appear in a diff; flag them instead of quoting them.
Output format
Subject: <type>(<scope>): <summary>
Body:
<why this change was made, context, tradeoffs>
Breaking changes: <none | description + migration notes>
Risk notes: <none | short risk callout>
Suggested command:
git commit -m "<subject>" -m "<body>"Quality checklist
- Subject uses imperative mood and a valid Conventional Commits type
- Subject is ≤72 characters
- Body explains motivation, not just mechanics
- Breaking changes are called out explicitly if present
- No secrets or credentials are echoed from the diff
- Commit was not executed automatically
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

